computer-vision-1

Generalized Few-Shot Semantic Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in generalized-few-shot-semantic-segmentation-1

Trend

Dataset

Best Model

Actions

PASCAL-5i (5-Shot)

PASCAL-5i (1-Shot)

Libraries

i

Use these libraries to find generalized-few-shot-semantic-segmentation-1 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Generalized Few-shot Semantic Segmentation

Jiaya Jia, Michelle Shu, Hengshuang Zhao, Xin Lai, Li Jiang, Zhuotao Tian•Sat Oct 10 2020

This paper introduces a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS- Seg), and proposes the Context-Aware Prototype Learning (CAPL) that significantly improves performance by leveraging the co-occurrence prior knowledge from support samples and dynamically enriching contextual information to the classifier, conditioned on the content of each query image.

104

Content

COCO-20i (1-shot)

COCO-20i (5-shot)

0

Paper Graph

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

Sina Hajimiri, Malik Boudiaf, Ismail Ben Ayed, J. Dolz•Thu Nov 24 2022

A simple yet effective model based on the well-known InfoMax principle, where the Mutual Information between the learned feature representations and their corresponding predictions is maximized, which yields substantial improvements on the popular few-shot segmentation benchmarks.

37 0

Paper Graph

Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation

Ting Yao, Hongtao Xie, Yiheng Zhang, Sun'ao Liu, Zhaofan Qiu, Yongdong Zhang•Wed May 31 2023

Generalized few-shot semantic segmentation (GFSS) distinguishes pixels of base and novel classes from the background simultaneously, conditioning on sufficient data of base classes and a few examples from novel class. A typical GFSS approach has two training phases: base class learning and novel class updating. Nevertheless, such a stand-alone updating process often compromises the well-learnt features and results in performance drop on base classes. In this paper, we propose a new idea of leveraging Projection onto Orthogonal Prototypes (POP), which updates features to identify novel classes without compromising base classes. POP builds a set of orthogonal prototypes, each of which represents a semantic class, and makes the prediction for each class separately based on the features projected onto its prototype. Technically, POP first learns prototypes on base data, and then extends the prototype set to novel classes. The orthogonal constraint of POP encourages the orthogonality between the learnt prototypes and thus mitigates the influence on base class features when generalizing to novel prototypes. Moreover, we capitalize on the residual of feature projection as the background representation to dynamically fit semantic shifting (i.e., background no longer includes the pixels of novel classes in updating phase). Extensive experiments on two benchmarks demonstrate that our POP achieves superior performances on novel classes without sacrificing much accuracy on base classes. Notably, POP outperforms the state-of-the-art fine-tuning by 3.93% overall mIoU on PASCAL-5i in 5-shot scenario.

39 0

Paper Graph

Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation

Yuming Fang, Guosheng Lin, Chuan-Sheng Foo, Weide Liu, Zhonghua Wu, Jun Cheng•Thu Mar 23 2023

This work proposes a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes.

22 0

Paper Graph

Adding a benchmark result helps the community track progress.